Negotiation in Multi-Agent Environments

Internet offers many choices of products, services and content. But the multitude of choices has altered the manner in which customers choose and buy products and services. Internet searching agents are tools allowing consumers to compare on-line Web-stores’ prices for a product. In the field of electronic commerce, consumers can already benefit from the use of searching agents that automatically query on-line sellers’ catalogues in order to gather information about available products. These agents have different degrees of sophistication and differ in their ability to process information. Intelligent agents in artificial intelligence are closely related to agents in economics. They can adapt to the needs of different users, it can learn new concepts and techniques, it can anticipate the needs of the user, and it can take initiative and make suggestions to the user. Negotiation is an important mechanism for resolving conflicts between individual or economic agents. Intelligent agents can provide services in filtering data, searching for information, online tutoring, and negotiation. In this chapter, we present a study that investigates how costly information could affect the performance of several types of searching agents in electronic commerce environments. The existing agents base their search on a predefined list of Web-stores and, as such, they can be qualified as fixed-sample size searching agents. However, with the implementation of new Internet pricing schemes, this search rule evolve toward more flexible search methods allowing for an explicit trade-off between the communication costs and the product price. In this setting, the sequential optimal search rule is a possible alternative. Nevertheless, its adoption depends on its expected performance. The main goal is to analyze the relative performances of two types of search agents on a virtual market with costly information. The following section reviews several existing agents to highlight their flaws and strengths. This review aims to test the theory that agents are a viable alternative to search engines.